A Robust Deep Learning Approach for Rock Discontinuity Identification from Large Scale 3D Point Clouds

A Robust Deep Learning Approach for Rock Discontinuity Identification from Large Scale 3D Point Clouds | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A Robust Deep Learning Approach for Rock Discontinuity Identification from Large Scale 3D Point Clouds Juanjuan Sun, Shu Zhu, Jinshan Sun, Jian Zhou, Yanbing Wang, Jiyong Zhang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7680514/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 18 You are reading this latest preprint version Abstract Rock discontinuities are critical geological features that govern rock mass mechanical behavior. Accurate identification and quantitative characterization of these discontinuities underpin vital applications for slope stability analysis, underground excavation design, and rock blasting. Conventional approaches to large-scale point cloud analysis are often limited by poor fine-scale feature representation and high parameter sensitivity. To address these limitations, this study proposes RL-JointNet, an end-to-end deep learning approach specifically developed for robust discontinuity segmentation. The key novelty of RL-JointNet lies in its enhanced local feature extraction module, which integrates explicit relative position encoding with a multi-path feature fusion strategy to better represent complex neighborhood geometries. The model's effectiveness was validated on high-resolution point cloud datasets from two rock slopes. Results demonstrate superior performance, achieving a Global Accuracy (GA) up to 98.7% and a mean Intersection over Union (mIoU) of 98.1%, with recognition accuracy for individual discontinuity classes consistently exceeding 95%. Crucially, a comprehensive hyperparameter sensitivity analysis revealed that RL-JointNet exhibits significantly enhanced robustness compared to conventional point cloud deep learning models, ensuring consistent performance across diverse engineering scenarios. The proposed RL-JointNet offers a reliable approach for automated discontinuity analysis, thereby enhancing the capability for detailed characterization of large-scale and complex rock masses. Physical sciences/Engineering Physical sciences/Mathematics and computing Earth and environmental sciences/Natural hazards Earth and environmental sciences/Solid earth sciences Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 13 Nov, 2025 Reviews received at journal 27 Oct, 2025 Reviews received at journal 24 Oct, 2025 Reviews received at journal 22 Oct, 2025 Reviews received at journal 22 Oct, 2025 Reviewers agreed at journal 22 Oct, 2025 Reviewers agreed at journal 22 Oct, 2025 Reviews received at journal 22 Oct, 2025 Reviewers agreed at journal 22 Oct, 2025 Reviewers agreed at journal 19 Oct, 2025 Reviews received at journal 08 Oct, 2025 Reviewers agreed at journal 06 Oct, 2025 Reviewers agreed at journal 03 Oct, 2025 Reviewers invited by journal 30 Sep, 2025 Editor invited by journal 30 Sep, 2025 Editor assigned by journal 26 Sep, 2025 Submission checks completed at journal 25 Sep, 2025 First submitted to journal 22 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7680514","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":527498144,"identity":"0cbacb2b-0c2f-4843-accd-f2e66690c3d7","order_by":0,"name":"Juanjuan Sun","email":"","orcid":"","institution":"Jianghan University","correspondingAuthor":false,"prefix":"","firstName":"Juanjuan","middleName":"","lastName":"Sun","suffix":""},{"id":527498145,"identity":"4fe8c9f0-0622-4c3e-8472-d0699686ec04","order_by":1,"name":"Shu Zhu","email":"","orcid":"","institution":"State Grid Economic and Technological Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Shu","middleName":"","lastName":"Zhu","suffix":""},{"id":527498146,"identity":"0bf72d60-010b-43cd-a42f-88eaeba3faa4","order_by":2,"name":"Jinshan Sun","email":"","orcid":"","institution":"Jianghan University","correspondingAuthor":false,"prefix":"","firstName":"Jinshan","middleName":"","lastName":"Sun","suffix":""},{"id":527498147,"identity":"54300b98-38f5-4aff-87de-0eb2a39000bc","order_by":3,"name":"Jian Zhou","email":"","orcid":"","institution":"Beijing University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Zhou","suffix":""},{"id":527498148,"identity":"2af9dde2-ac63-4677-ad51-b18f6998a1c2","order_by":4,"name":"Yanbing Wang","email":"","orcid":"","institution":"State Grid Economic and Technological Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Yanbing","middleName":"","lastName":"Wang","suffix":""},{"id":527498149,"identity":"d0457af4-20ed-4a15-a66d-57d2a246b61f","order_by":5,"name":"Jiyong Zhang","email":"","orcid":"","institution":"State Grid Economic and Technological Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Jiyong","middleName":"","lastName":"Zhang","suffix":""},{"id":527498150,"identity":"943c8d2f-22dc-40e7-8c50-c3cf72a17d3c","order_by":6,"name":"Xueliang Wang","email":"data:image/png;base64,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","orcid":"","institution":"Institute of Geology and Geophysics","correspondingAuthor":true,"prefix":"","firstName":"Xueliang","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-09-22 15:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7680514/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7680514/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-31137-4","type":"published","date":"2025-12-16T15:58:17+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93364816,"identity":"5fecef1d-acac-4cd8-9cb3-920f47ad5c75","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11748205,"visible":true,"origin":"","legend":"","description":"","filename":"ScientificReportsmanuscriptARobustDeepLearningApproachforRockDiscontinuityIdentificationfromLargeScale3DPointClouds.docx","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/a2606ebeca263c56d5b444c4.docx"},{"id":93364807,"identity":"2d0f0609-7520-45fe-b507-ef4cc45dd286","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8623,"visible":true,"origin":"","legend":"","description":"","filename":"0661316612f945258cfa3adff20b97dc.json","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/7ba8d56d31446e8aecbe09aa.json"},{"id":93364813,"identity":"f43c4655-e6eb-4781-9446-512d0378ce76","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":158855,"visible":true,"origin":"","legend":"","description":"","filename":"0661316612f945258cfa3adff20b97dc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/04259b8ebeaf885dce0370e6.xml"},{"id":93364809,"identity":"83676ca7-5cff-444d-a034-d2b5263f7245","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":228627,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/13737d4134b9ceff881f598e.png"},{"id":93364808,"identity":"59678d01-a47a-48ad-b687-75ee66f409dc","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70163,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/7841eee23e21694903d9c7ee.png"},{"id":93365486,"identity":"b602da9d-8a47-4901-8f53-c8ab2c4585dd","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":656943,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/4076b7a2cc46a8956791dc8d.png"},{"id":93364811,"identity":"225625b1-d447-4ee2-bfc2-b3e908c02bea","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":291664,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/843e859f1791ebe13c081cdc.png"},{"id":93365485,"identity":"85e97dc0-ff3c-4490-9f1d-82c1faafc805","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":660637,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/be5927bbd40a5f736bde47ed.jpeg"},{"id":93365483,"identity":"f5b40f12-7814-4ad4-8bf0-22d28a1e4ff3","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":543165,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/72c2554c2a4c0a5ec804781d.png"},{"id":93365487,"identity":"5bb0a2ff-e8ca-418c-9929-f9c3e25b74f0","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":351858,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/0bdbf4f1a9b475ca04fc9701.jpeg"},{"id":93364818,"identity":"bb2907d6-2d60-4097-bdba-2d98534eec8e","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1022606,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/574819f13662e5faa375db58.jpeg"},{"id":93365489,"identity":"657c9d6d-9dc1-46b2-ae08-8547bad622a7","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":466729,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/51be778f92e245d1ecc8ba74.png"},{"id":93364835,"identity":"78e2200a-ccaf-4fbf-a5e3-51e28480fe16","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"emf","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4195412,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.emf","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/79d20bf34bed422c57006489.emf"},{"id":93364821,"identity":"cb1df584-ced9-4898-9191-97432e9a4737","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1759,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/7a194c1c12907d149fd25459.png"},{"id":93365629,"identity":"d114928f-ced5-43cb-b93f-9a7ebf7affc2","added_by":"auto","created_at":"2025-10-13 04:48:43","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2271,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/78841c7170a3910868d9e906.png"},{"id":93364820,"identity":"327614bb-379c-4c82-82b8-6c2a0f5e664e","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4009,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/944ff434a3dba4cd074588e8.png"},{"id":93364815,"identity":"ba986f8c-eb6d-4477-925d-67968d334326","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67723,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/6a38230fa1b660ffa8907805.png"},{"id":93364824,"identity":"9b3284ab-abd5-4fb9-ab7d-f1f66db1dd99","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":402478,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/5da61afb81a9694fe5c7f1e5.png"},{"id":93365488,"identity":"f15e3cb6-a8a6-4124-a655-fdb6aae59afb","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61444,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/4945c5e7bf2b6a338fa7a8c3.png"},{"id":93364837,"identity":"82eed6aa-3920-479e-894f-71e22eb21ff4","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19837,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/e5066a5a9a0a0f852b0a7743.png"},{"id":93365630,"identity":"0d88aedb-97a4-4be8-9b1e-bffa965ce49c","added_by":"auto","created_at":"2025-10-13 04:48:43","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76059,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/83d151b63de42d869a1265e4.png"},{"id":93365491,"identity":"be77faea-bf7a-4842-b2cd-073da6cfcb9f","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31890,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/d705c8f419cf3b02db224570.png"},{"id":93365493,"identity":"db5c2436-93fb-4ff1-939f-39bcf581eca8","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":200561,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/06f2a790550eb282579f2de1.png"},{"id":93365496,"identity":"045933e5-7caa-44d1-98f0-bdc2430b7335","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":113421,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/ce8cb0c4e2e9b80aafa23ea9.png"},{"id":93365494,"identity":"8c85ab54-cdf3-4b3e-9c04-8e09f448a14a","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93168,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/81400ffffe067421afbba750.png"},{"id":93364822,"identity":"edc27787-c96e-4af6-a221-a8380d465370","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":377504,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/88b3ea16bd5562c54e1b2dc5.png"},{"id":93364833,"identity":"23c5f20d-1352-4b6b-b05c-f6a0928b3cda","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84162,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/b0f47697aeb7358573869c9f.png"},{"id":93365492,"identity":"9488398d-67d8-4ca3-944d-0146e388617b","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":280437,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/a5eb8538279e071642924a35.png"},{"id":93364831,"identity":"bba80df4-855b-4188-847f-ce02201cdd2b","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1301,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/355496be02d2e56fb478cadb.png"},{"id":93364841,"identity":"3ee4841f-251e-4102-a7a2-6944a4000eb8","added_by":"auto","created_at":"2025-10-13 04:32:44","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1642,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/30942a90ccc4637ebd80c90d.png"},{"id":93364830,"identity":"b711111b-6561-43b7-80a0-4f63fcc68b65","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2267,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/9514f3da8e7429bf43a11bba.png"},{"id":93364827,"identity":"b0b6c9bb-82bf-43ba-918e-a0ae17e5aa72","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16570,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/40a37b4f7fc5a626b8be94e7.png"},{"id":93365495,"identity":"deef1041-6b3e-4688-82cb-06ef3cce6480","added_by":"auto","created_at":"2025-10-13 04:40:43","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67843,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/8d25c11c6210cb20c3c0180f.png"},{"id":93364839,"identity":"73fd958d-9047-4f68-94e1-e9ab360286db","added_by":"auto","created_at":"2025-10-13 04:32:44","extension":"xml","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159155,"visible":true,"origin":"","legend":"","description":"","filename":"0661316612f945258cfa3adff20b97dc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/fde44c6b99141d88719c1f78.xml"},{"id":93364826,"identity":"271ae6e7-fee8-4632-be33-889eea138101","added_by":"auto","created_at":"2025-10-13 04:32:43","extension":"html","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174546,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1/af3fe0c0428d78df379d8d89.html"},{"id":98814006,"identity":"be7b3b8a-887c-4cd8-87f1-6c1e38cff3dc","added_by":"auto","created_at":"2025-12-22 16:09:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1354748,"visible":true,"origin":"","legend":"","description":"","filename":"ScientificReportsmanuscriptARobustDeepLearningApproachforRockDiscontinuityIdentificationfromLargeScale3DPointClouds.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7680514/v1_covered_0d70e62b-803b-40f6-b19c-6717daad734b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Robust Deep Learning Approach for Rock Discontinuity Identification from Large Scale 3D Point Clouds","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7680514/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7680514/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRock discontinuities are critical geological features that govern rock mass mechanical behavior. Accurate identification and quantitative characterization of these discontinuities underpin vital applications for slope stability analysis, underground excavation design, and rock blasting. Conventional approaches to large-scale point cloud analysis are often limited by poor fine-scale feature representation and high parameter sensitivity. To address these limitations, this study proposes RL-JointNet, an end-to-end deep learning approach specifically developed for robust discontinuity segmentation. The key novelty of RL-JointNet lies in its enhanced local feature extraction module, which integrates explicit relative position encoding with a multi-path feature fusion strategy to better represent complex neighborhood geometries. The model's effectiveness was validated on high-resolution point cloud datasets from two rock slopes. Results demonstrate superior performance, achieving a Global Accuracy (GA) up to 98.7% and a mean Intersection over Union (mIoU) of 98.1%, with recognition accuracy for individual discontinuity classes consistently exceeding 95%. Crucially, a comprehensive hyperparameter sensitivity analysis revealed that RL-JointNet exhibits significantly enhanced robustness compared to conventional point cloud deep learning models, ensuring consistent performance across diverse engineering scenarios. The proposed RL-JointNet offers a reliable approach for automated discontinuity analysis, thereby enhancing the capability for detailed characterization of large-scale and complex rock masses.\u003c/p\u003e","manuscriptTitle":"A Robust Deep Learning Approach for Rock Discontinuity Identification from Large Scale 3D Point Clouds","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-13 04:32:38","doi":"10.21203/rs.3.rs-7680514/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-13T08:34:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-27T14:54:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-24T07:19:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-23T00:48:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-22T23:52:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"56914964258233552324208885046000478223","date":"2025-10-22T06:01:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"41077143776796527430716502288392831985","date":"2025-10-22T04:54:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-22T04:53:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"21468376176581349633625221382911866792","date":"2025-10-22T04:50:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"212691875784372579138839852130866984474","date":"2025-10-19T15:14:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-09T02:17:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"116039403588567693470594865717655450836","date":"2025-10-07T03:39:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"49296703866810005262050157598165061971","date":"2025-10-03T15:15:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-30T07:27:40+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-30T06:40:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-26T18:04:01+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-25T10:56:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-22T11:06:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"561dc80b-24e5-4cb7-888d-bd710d62a124","owner":[],"postedDate":"October 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":56067373,"name":"Physical sciences/Engineering"},{"id":56067374,"name":"Physical sciences/Mathematics and computing"},{"id":56067375,"name":"Earth and environmental sciences/Natural hazards"},{"id":56067376,"name":"Earth and environmental sciences/Solid earth sciences"}],"tags":[],"updatedAt":"2025-12-22T16:02:56+00:00","versionOfRecord":{"articleIdentity":"rs-7680514","link":"https://doi.org/10.1038/s41598-025-31137-4","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-16 15:58:17","publishedOnDateReadable":"December 16th, 2025"},"versionCreatedAt":"2025-10-13 04:32:38","video":"","vorDoi":"10.1038/s41598-025-31137-4","vorDoiUrl":"https://doi.org/10.1038/s41598-025-31137-4","workflowStages":[]},"version":"v1","identity":"rs-7680514","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7680514","identity":"rs-7680514","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}